Re: Seeing context switch storm with 10/13 snapshot of

From: Simon Riggs <simon(at)2ndquadrant(dot)com>
To: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Cc: Robert Creager <Robert(dot)Creager(at)Sun(dot)com>, PGHackers <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: Seeing context switch storm with 10/13 snapshot of
Date: 2005-10-24 22:46:34
Message-ID: 1130193994.8300.1117.camel@localhost.localdomain
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Fri, 2005-10-21 at 17:17 -0400, Tom Lane wrote:
> Simon Riggs <simon(at)2ndquadrant(dot)com> writes:
> > Certainly there is a lack of ideas as to how to fix it, as you mention
> > in (3). This shows to me that the solution lies in one of two areas: a)
> > the solution has not yet been considered or b) the solution has already
> > been thought of and for whatever reason disregarded. You may be certain
> > that the solution lies in a), though I am not. Rejecting ideas quickly
> > may simply increase the chances of finding the solution in a b) case.
>
> However, building a spinlock test harness presupposes that the solution
> lies in the spinlock code itself

(I thought I had said) that was actually the main test, rather than a
presupposition. The solution may lie there or not and when it is built
we would be able to determine where it is. If the issue is with the
spinlock code itself, it will then help us find the solution. If it is
not, then we will know to look elsewhere.

It is important that we isolate the problem in such a way that others
can help fix it. If we do it only within the database, then the special
context will force many to say they cannot help us.

> patterns of it. So I'd throw the "rejecting ideas too quickly"
> challenge right back at you.

My words were inspired by a desire to leave the Doldrums only, not to
cause other issues. I apologise for any offence given.

> What we need to optimize is the behavior
> in the real context of Postgres, not in a test harness.

That is the end goal, yes.

My sub-goal on that path is problem isolation (only).

Best Regards, Simon Riggs

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Russell Smith 2005-10-24 22:51:59 Re: BUG #1993: Adding/subtracting negative time intervals
Previous Message Bruce Momjian 2005-10-24 22:41:41 Re: New timezone data